Measuring how AI agents handle everyday wet-lab science
OpenAI introduces BioBasicsBench, a 100-task benchmark measuring how well AI agents interpret raw experimental data and handle everyday wet-lab science.
AI NEWS JOURNAL
Search AI news
Search headlines, summaries and articles to connect the dots.
Migrating vLLM to the LibTorch Stable ABI
How vLLM migrated its CUDA build and compiled dependencies to the LibTorch Stable ABI, enabling compatible PyTorch upgrades without rebuilding vLLM.
Oracle wants to pull stalled AI agents out of demo mode and into production
Companies want AI agents faster than they can build the AI architecture to run them. Most can put together a convincing demo. Far fewer can move agents into production without exposing data, hurting uptime or blowing their budgets. That gap is pushing database providers to rethink what a data platform for agents has to deliver. […] The post Oracle wants to pull stalled AI agents out of demo mode and into production appeared first on SiliconANGLE.
ProcessPrefBench: Evaluating Cross-Task Transfer of Individual Process Preferences from Naturalistic Human-AI Interaction
arXiv:2611.06065v1 Announce Type: new Abstract: In natural human-AI dialogue, users' corrections, requests, and self-descriptions carry reusable signals about how they want work to be done. These signals reveal individual process preferences, user-specific standards for evidence, depth, analytical focus, procedure, and delivery. We ask whether a preference revealed in one dialogue can shape an assistant's later answer when the task does not restate it. ProcessPrefBench uses three months of natural dialogues from two knowledge workers to build 66 source-target cases separately judged for source evidence and target applicability. Sources are preselected, so the benchmark tests application rather than retrieval. We test three models with target-only, full-history, and distilled-preference prompts. Target-specific 0-2 rubrics score preference realization, and a task gate flags severe failures. Compared with target-only prompting, full-history and imperative distilled-preference prompting raise preference realization by 0.204 and 0.244 points on the 0-2 scale, respectively, with no reliable advantage from distillation. Fabricated-evidence failures rise from 5.8% under target-only prompting to 10.1% under full-history and 10.4% under imperative prompting. ProcessPrefBench highlights a tension in learning from dialogue, where drawing on prior interactions can improve preference realization yet also invite fabricated evidence. We hope it helps build assistants that honor a user's process preferences without sacrificing factual reliability.
Show HN: Antidraw – Open-source AI prototyping canvas for any React library
Article URL: https://github.com/AntidrawHQ/antidraw Comments URL: https://news.ycombinator.com/item?id=50391875 Points: 3 # Comments: 1
Show HN: Convert recorded class lectures into PDF/eBooks
Article URL: https://lecturetobook.com/ Comments URL: https://news.ycombinator.com/item?id=50386766 Points: 1 # Comments: 0
Show HN: Flawless UI/UX – A design skill and inspection CLI for coding agents
Article URL: https://github.com/smokeeaasd/flawless-ui-ux Comments URL: https://news.ycombinator.com/item?id=50381846 Points: 1 # Comments: 0
Show HN: Lab Canary – Rating AI labs on whether their staff can speak up
Article URL: https://labcanary.com/ Comments URL: https://news.ycombinator.com/item?id=50386089 Points: 3 # Comments: 0
Show HN: Ls-service – minimal, namespaced, and typed localStorage wrapper
Article URL: https://github.com/brysonbw/ls-service Comments URL: https://news.ycombinator.com/item?id=50383396 Points: 1 # Comments: 0
Show HN: Overhead – the planes overhead, painted on an e-ink frame
Hi HN,I've been fascinated by aviation for some time now. Inspired by Fugleramme, I wanted a framed print of a cluster of aircraft over my house or a busy airport. So I built Overhead. (Photos in the README)The hero photo shows planes departing and landing in Changi, Singapore.How it worksFlight data for a location is gathered from adsb.lol and adsb.fi as a fallback. (you can also point it to your own ADS-B receiver).The photo of the exact aircraft is gathered from planespotters.net and the photographer is credited on the page.The photo is then handed to an AI image gen service via fal.ai using your own key.It's then cut out and packed into a cluster on the page with packers adapted from Fugleramme.It costs about US$0.04 a painting but images are painted once and kept for the next time that aircraft is seen.You can also choose to only show photos.This widget is built on my open source, self-hosted e-ink platform, Tesserae. It's a one click install from the widget catalog.I'm looking for feedback and contributors.https://github.com/arnegiacomo/fugleramme https://github.com/dmellok/tesserae Comments URL: https://news.ycombinator.com/item?id=50390605 Points: 1 # Comments: 0
Show HN: Repairer – close the breach when a Linux flaw goes public
As we've seen with the Ubuntu critical CVE-2026-98432 (CVSS 9.8), AI-dicovered zero day exploit are being reported at an exponential rate and we don't have the process for dealing with the flood of exploits in real time.What we need is an AI-based system for autopatching systems based on real time information. The vendor's fix can take days or weeks to be out (is the Ubuntu thing patched yet?) and meanwhile the grid is vulnerable to exploitation, especially AI worms.Repairer is a small program that runs on each of your servers. The day an exploit goes public it puts up a stopgap that blocks it, and once the real fix is up it takes the stopgap back off by itself.A stopgap only takes something away — drop certain packets, turn off a kernel module or service, remove a setuid bit. It never opens a port, installs or downloads anything, nor runs code. It arms an undo playbook before applying the stopgap, so the change reverts if affects any services.It only ever acts on rules you sign with a (hardware) crypto wallet.Let's go further: stopgaps are written and checked by a swarm of AI agents (gnosh.ai sessions) running on gno.land, each with bonded stake. Each stopgap is run on fresh machines, and whoever is caught lying loses their stake to whoever caught them.The agent is built and tested on Ubuntu and Debian, all open source, standard-library Go. More distros coming. Let's build repairer together.https://gno.security/repairer/ https://github.com/gnosecurity/repairer Comments URL: https://news.ycombinator.com/item?id=50388417 Points: 1 # Comments: 1
The Wizard of Open Weights: Chris Alexiuk Makes AI Easy With Open Models
Chris Alexiuk has a simple rule about open source AI: If you believe in it, be loud about it. “We should be shouting about this technology from the rooftops,” said Alexiuk, a Toronto-based senior product research engineer in deep learning at NVIDIA who specializes in making open large language models (LLMs) practical for working developers. […]
University of Utah retains operational sovereignty as Redtail expands research access
Operational sovereignty gives universities authority over how shared computing resources are allocated, managed and secured. The University of Utah’s Redtail AI factory supercomputer brings advanced computing capabilities to a statewide community. Supporting researchers, students, administrators and external partners through that infrastructure requires more than computing capacity, according to Manish Parashar (pictured), chief AI officer of […] The post University of Utah retains operational sovereignty as Redtail expands research access appeared first on SiliconANGLE.
Agile Deliberation: How AI helps humans define the gray areas
Data Mining & Modeling
Certinia brings AI into professional services workflows
Certinia Inc. is bringing AI into the software firms use to sell projects, assign staff, deliver work and bill clients. AI’s ability to instantaneously draw from a deep well of information and provide guidance in practically any field of expertise has changed the paradigm for professional services. For Certinia Inc., whose business facilitates 7.1 billion […] The post Certinia brings AI into professional services workflows appeared first on SiliconANGLE.
Clearing up a robot’s fuzzy memory
A new system identifies and corrects unreliable object descriptions stored in a robot’s memory, improving the robot’s ability to interact with its environment.
Craft and taste
What does old me think
Dharma Field Extractor: Any Document In, Structured Fields in JSON Out
The Dharma Field Extractor, a 2-billion-parameter model, specializes in extracting specific fields from diverse document types—such as invoices, IDs, and medical forms—into structured JSON format. It outperforms general-purpose frontier LLMs in accuracy and reduces cost by up to 147 times when self-hosted, demonstrating that domain-specialized small models can surpass large general-purpose models on well-defined tasks. The model supports both open extraction (detecting fields without a schema) and schema-directed extraction (returning exact field names and types), with training data spanning English, Brazilian Portuguese, and multilingual documents. Benchmarks show superior F1 scores and valid JSON output across real-world datasets like SROIE and FUNSD, reinforcing the thesis that specialization beats scale for enterprise document processing.
Exclusive: Aina’s Smart Ring Wants to Be a Remote Control for Your AI Agent
The startup Aina bets you won’t need to rely on your phone to control virtual assistants. It’s making a smart ring that lets you control the actions of your autonomous agents with one tap.
Faster Retrieval for Better, More Efficient RAG
Maximum inner product search (MIPS) sits at the core of recommendation systems, search, and retrieval-augmented generation (RAG). Given a query vector, MIPS systems search within a database of millions of candidate key vectors for the one that best matches the query. The original data point associated with that best-matching key is then used to handle the query: in RAG, the document that is best suited to answer the question is typically prefixed to the query. As the number of keys grows to millions and vector dimensions reach thousands, the computational cost of running an exhaustive…